Task (computing)

About: Task (computing) is a research topic. Over the lifetime, 9718 publications have been published within this topic receiving 129364 citations.

Task scheduling method, device and system

Abstract: An embodiment of the invention discloses a task scheduling method, device and system. The method comprises the steps of obtaining computing resource information of computing nodes and allocating the idle computing resources to computing frames according to the information, wherein the computing resource information of the computing nodes includes the using conditions of various types of computing resources of the computing nodes; respectively allocating the idle computing resources obtained by the computing frames to tasks in task queues of the computing frames. By applying the task scheduling method, device and system, diversity of the computing resources is considered when the computing resource information of the computing nodes is obtained, so that the computing resources allocated to the tasks are reasonable.

Latent Collaborative Retrieval

Abstract: Retrieval tasks typically require a ranking of items given a query. Collaborative filtering tasks, on the other hand, learn to model user's preferences over items. In this paper we study the joint problem of recommending items to a user with respect to a given query, which is a surprisingly common task. This setup differs from the standard collaborative filtering one in that we are given a query x user x item tensor for training instead of the more traditional user x item matrix. Compared to document retrieval we do have a query, but we may or may not have content features (we will consider both cases) and we can also take account of the user's profile. We introduce a factorized model for this new task that optimizes the top-ranked items returned for the given query and user. We report empirical results where it outperforms several baselines.

Resource Allocation in the Brain

Abstract: When an individual performs several tasks simultaneously, processing resources must be allocated to dierent brain systems to produce energy for neurons to re. Following the evidence from neuroscience, we model the brain as an organization in which a coordinator allocates limited resources to the brain systems responsible for the dierent tasks. Systems are privately informed about the amount of resources necessary to perform their task and compete to obtain the resources. The coordinator arbitrates the demands while satisfying the resource constraint. We show that the optimal mechanism is to impose to each system with privately known needs a cap in resources that depends negatively on the amount of resources requested by the other system. This allocation can be implemented using a biologically plausible mechanism. Finally, we provide some implications of our theory: (i) performance can be awless for suciently simple tasks, (ii) the dynamic allocation rule exhibits inertia (current allocations are increasing in past needs), and (iii) dierent cognitive tasks are performed by dierent systems only if the tasks are suciently important.

Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference

Abstract: Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-task models are often overlooked in literature. First, enabling the model to be inherently incremental, continuously incorporating information from new tasks without forgetting the previously learned ones (incremental learning). Second, eliminating adverse interactions amongst tasks, which has been shown to significantly degrade the single-task performance in a multi-task setup (task interference). In this paper, we show that both can be achieved simply by reparameterizing the convolutions of standard neural network architectures into a non-trainable shared part (filter bank) and task-specific parts (modulators), where each modulator has a fraction of the filter bank parameters. Thus, our reparameterization enables the model to learn new tasks without adversely affecting the performance of existing ones. The results of our ablation study attest the efficacy of the proposed reparameterization. Moreover, our method achieves state-of-the-art on two challenging multi-task learning benchmarks, PASCAL-Context and NYUD, and also demonstrates superior incremental learning capability as compared to its close competitors. The code and models are made publicly available (https://github.com/menelaoskanakis/RCM).

Migrating tasks between asymmetric computing elements of a multi-core processor

Abstract: In one embodiment, the present invention includes a multicore processor having first and second cores to independently execute instructions, the first core visible to an operating system (OS) and the second core transparent to the OS and heterogeneous from the first core. A task controller, which may be included in or coupled to the multicore processor, can cause dynamic migration of a first process scheduled by the OS to the first core to the second core transparently to the OS. Other embodiments are described and claimed.